[MODERATED] [PATCH v4 18/28] MDSv4 26

[Andi Kleen <andi@firstfloor.org>]

From: Andi Kleen <ak@linux.intel.com>
Subject:  mds: Clear cpu on all timers, unless the timer
 opts-out

By default we assume timers might touch user data and schedule
a cpu clear on next kernel exit.

Support opt-outs where timer and hrtimer handlers can opt-in
they they don't touch any user data.

Note this takes one bit from the timer wheel index field away,
but it seems there are less wheels available anyways, so that
should be ok.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 include/linux/hrtimer.h | 4 ++++
 include/linux/timer.h   | 9 ++++++---
 kernel/time/hrtimer.c   | 5 +++++
 kernel/time/timer.c     | 8 ++++++++
 4 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 2e8957eac4d4..b32c76919f78 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -32,6 +32,7 @@ struct hrtimer_cpu_base;
  *				  when starting the timer)
  * HRTIMER_MODE_SOFT		- Timer callback function will be executed in
  *				  soft irq context
+ * HRTIMER_MODE_NO_USER		- Handler does not touch user data.
  */
 enum hrtimer_mode {
 	HRTIMER_MODE_ABS	= 0x00,
@@ -48,6 +49,7 @@ enum hrtimer_mode {
 	HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
 	HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
 
+	HRTIMER_MODE_NO_USER	= 0x08,
 };
 
 /*
@@ -101,6 +103,7 @@ enum hrtimer_restart {
  * @state:	state information (See bit values above)
  * @is_rel:	Set if the timer was armed relative
  * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
+ * @no_user:	function does not touch user data.
  *
  * The hrtimer structure must be initialized by hrtimer_init()
  */
@@ -112,6 +115,7 @@ struct hrtimer {
 	u8				state;
 	u8				is_rel;
 	u8				is_soft;
+	u8				no_user;
 };
 
 /**
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 7b066fd38248..222e72432be3 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -56,10 +56,13 @@ struct timer_list {
 #define TIMER_DEFERRABLE	0x00080000
 #define TIMER_PINNED		0x00100000
 #define TIMER_IRQSAFE		0x00200000
-#define TIMER_ARRAYSHIFT	22
-#define TIMER_ARRAYMASK		0xFFC00000
+#define TIMER_NO_USER		0x00400000
+#define TIMER_ARRAYSHIFT	23
+#define TIMER_ARRAYMASK		0xFF800000
 
-#define TIMER_TRACE_FLAGMASK	(TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE)
+#define TIMER_TRACE_FLAGMASK	\
+	(TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE | \
+	 TIMER_NO_USER)
 
 #define __TIMER_INITIALIZER(_function, _flags) {		\
 		.entry = { .next = TIMER_ENTRY_STATIC },	\
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index f5cfa1b73d6f..e2c8776ba2a4 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -42,6 +42,7 @@
 #include <linux/timer.h>
 #include <linux/freezer.h>
 #include <linux/compat.h>
+#include <linux/clearcpu.h>
 
 #include <linux/uaccess.h>
 
@@ -1276,6 +1277,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 		clock_id = CLOCK_MONOTONIC;
 
 	base += hrtimer_clockid_to_base(clock_id);
+	timer->no_user = !!(mode & HRTIMER_MODE_NO_USER);
 	timer->is_soft = softtimer;
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
@@ -1390,6 +1392,9 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	trace_hrtimer_expire_exit(timer);
 	raw_spin_lock_irq(&cpu_base->lock);
 
+	if (!timer->no_user)
+		lazy_clear_cpu();
+
 	/*
 	 * Note: We clear the running state after enqueue_hrtimer and
 	 * we do not reprogram the event hardware. Happens either in
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 444156debfa0..e6ab6986ffc8 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -43,6 +43,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/clearcpu.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -1338,6 +1339,13 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 		 */
 		preempt_count_set(count);
 	}
+
+	/*
+	 * The timer might have touched user data. Schedule
+	 * a cpu clear on the next kernel exit.
+	 */
+	if (!(timer->flags & TIMER_NO_USER))
+		lazy_clear_cpu();
 }
 
 static void expire_timers(struct timer_base *base, struct hlist_head *head)
-- 
2.17.2